Assessing the Value of ChatGPT for Clinical Decision Support Optimization

Liu, Siru; Wright, Aileen P.; Patterson, Barron L.; Wanderer, Jonathan P.; Turer, Robert W; Nelson, Scott D.; McCoy, Allison B.; Sittig, Dean F.; Wright, Adam

doi:10.1101/2023.02.21.23286254

Cited by 42 publications

(25 citation statements)

References 32 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[87, 86, 4, 68] evaluate the application of ChatGPT in clinical workflow. In [87], ChatGPT is used to decide the appropriate imaging procedure (e.g., Mammography, MRI, US, etc.)…”

Section: Methodsmentioning

confidence: 99%

“…The letters are evaluated from the perspective of factual correctness and humanness by clinicians, and ChatGPT achieved high scores on both criteria. In [68], ChatGPT is supplied with seven types of clinical decision support (CDS) alerts (e.g., pediatrics bronchiolitis, immunization, postoperative anesthesia nausea and vomiting, etc.) and asked to give suggestions.…”

Section: Methodsmentioning

confidence: 99%

“…The following of the review will show that existing publications on ChatGPT in healthcare can all find a proper categorization based on the proposed taxonomy. [40], [28], [76], [48], [24], [86] consultation [42], [66], [20], [41] clinical workflow [69], [68], [4], [ Besides the taxonomy, we further assign a tag (Level 1 -Level 3 ) to the selected papers to indicate the depth and particularity of the papers on the 'ChatGPT in Healthcare' topic:…”

Section: Taxonomymentioning

confidence: 99%

See 2 more Smart Citations

ChatGPT in Healthcare: A Taxonomy and Systematic Review

Li¹,

Amin²,

Kleesiek³

et al. 2023

Preprint

View full text Add to dashboard Cite

The recent release of ChatGPT, a chat bot research project/product of natural language processing (NLP) by OpenAI, stirs up a sensation among both the general public and medical professionals, amassing a phenomenally large user base in a short time. This is a typical example of the 'productization' of cutting-edge technologies, which allows the general public without a technical background to gain firsthand experience in artificial intelligence (AI), similar to the AI hype created by AlphaGo (DeepMind Technologies, UK) and self-driving cars (Google, Tesla, etc.). However, it is crucial, especially for healthcare researchers, to remain prudent amidst the hype. This work provides a systematic review of existing publications on the use of ChatGPT in healthcare, elucidating the 'status quo' of ChatGPT in medical applications, for general readers, healthcare professionals as well as NLP scientists. The large biomedical literature databasePubMedis used to retrieve published works on this topic using the keyword 'ChatGPT'. An inclusion criterion and a taxonomy are further proposed to filter the search results and categorize the selected publications, respectively. It is found through the review that the current release of ChatGPT has achieved only moderate or 'passing' performance in a variety of tests, and is unreliable for actual clinical deployment, since it is not intended for clinical applications by design. We conclude that specialized NLP models trained on (bio)medical datasets still represent the right direction to pursue for critical clinical applications.

show abstract

“…[87, 86, 4, 68] evaluate the application of ChatGPT in clinical workflow. In [87], ChatGPT is used to decide the appropriate imaging procedure (e.g., Mammography, MRI, US, etc.)…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Taxonomymentioning

confidence: 99%

See 1 more Smart Citation

ChatGPT in Healthcare: A Taxonomy and Systematic Review

Li¹,

Amin²,

Kleesiek³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…It can be useful for tests, final diagnoses, and management using clinical vignettes with a variety of age, gender identity, and emergency severity indices. 23 ChatGPT can generate useful suggestions for improving clinical decision support logic that are “…highly understandable and relevant…” 24 Future potential uses of AI for clinical practice include real-time monitoring of vital signs and laboratory values to identify patterns and trends. This pattern recognition could allow early intervention, personalized treatment recommendations, and triage of patients through telemedicine.…”

Section: Chatgpt For the Clinicianmentioning

confidence: 99%

The Genie Is Out of the Bottle

Morales-Ramirez,

Mishek,

Dasgupta

2023

Obstetrics &Amp; Gynecology

View full text Add to dashboard Cite

ChatGPT is a cutting-edge artificial intelligence technology that was released for public use in November 2022. Its rapid adoption has raised questions about capabilities, limitations, and risks. This article presents an overview of ChatGPT, and it highlights the current state of this technology for the medical field. The article seeks to provide a balanced perspective on what the model can and cannot do in three specific domains: clinical practice, research, and medical education. It also provides suggestions on how to optimize the use of this tool.

show abstract

“…The daunting challenge requires critical and insightful analysis of the data by expert minds to discern reliable data, which is not simply possible by text mining. In clinical medicine, the preliminary studies suggest that ChatGPT could generate reasonably but not perfectly accurate responses to medical questions, write patient clinic letters, or summarize discharge notes [2][3][4][5][6] . However, all ChatGPTgenerated medical documents must be reviewed and verified by experts.…”

mentioning

confidence: 99%

ChatGPT and other artificial intelligence chatbots and biomedical writing

2023

J Cardiovasc Aging

View full text Add to dashboard Cite

We asked ChatGPT whether it should be listed as an author of the text that it generates in response to questions. Here is how it responded: "Hello! As an AI language model, I don't have a personal identity or consciousness in the traditional sense, and I don't create content on my own. I was created by OpenAI, a research organization, and trained on vast amounts of text from the internet to generate human-like language in response to user prompts. However, the content that I generate is still subject to copyright laws, and the ownership of the content that I generate depends on the specific context and use case. In general, if someone uses my responses in a creative work, they would likely be considered the author of that work, but the original content generated by me would still be subject to copyright laws and owned by OpenAI."Well said, ChatGPT! Not applicable.

show abstract

Assessing the Value of ChatGPT for Clinical Decision Support Optimization

Cited by 42 publications

References 32 publications

ChatGPT in Healthcare: A Taxonomy and Systematic Review

ChatGPT in Healthcare: A Taxonomy and Systematic Review

The Genie Is Out of the Bottle

ChatGPT and other artificial intelligence chatbots and biomedical writing

Contact Info

Product

Resources

About